Towards Automated Crowdsourced Testing via Personified-LLM

TL;DR

This paper introduces PersonaTester, a personified-LLM framework that simulates diverse human-like behaviors in automated GUI testing, improving test effectiveness and realism over traditional automated methods.

Contribution

The paper presents a novel persona-injected LLM framework for automated crowdsourced GUI testing, capturing behavioral diversity and enhancing bug detection capabilities.

Findings

PersonaTester reproduces real crowdworker behaviors with high intra-persona consistency.

Persona-guided testing yields more crashes and functional bugs than baseline methods.

The framework achieves over 117% improvement in behavioral variability compared to baseline.

Abstract

The rapid proliferation and increasing complexity of software demand robust quality assurance, with graphical user interface (GUI) testing playing a pivotal role. Crowdsourced testing has proven effective in this context by leveraging the diversity of human testers to achieve rich, scenario-based coverage across varied devices, user behaviors, and usage environments. In parallel, automated testing, particularly with the advent of large language models (LLMs), offers significant advantages in controllability, reproducibility, and efficiency, enabling scalable and systematic exploration. However, automated approaches often lack the behavioral diversity characteristic of human testers, limiting their capability to fully simulate real-world testing dynamics. To address this gap, we present PersonaTester, a novel personified-LLM-based framework designed to automate crowdsourced GUI testing. By injecting representative personas, defined along three orthogonal dimensions: testing mindset, exploration strategy, and interaction habit, into LLM-based agents, PersonaTester enables the simulation of diverse human-like testing behaviors in a controllable and repeatable manner. Experimental results demonstrate that PersonaTester faithfully reproduces the behavioral patterns of real crowdworkers, exhibiting strong intra-persona consistency and clear inter-persona variability (117.86% -- 126.23% improvement over the baseline). Moreover, persona-guided testing agents consistently generate more effective test events and trigger more crashes (100+) and functional bugs (11) than the baseline without persona, thus substantially advancing the realism and effectiveness of automated crowdsourced GUI testing.